Menu
Skills in this repository
SkillsMP has collected 5,417 skills from majiayu000/claude-skill-registry. Open a skill to review its source and details.
majiayu000/claude-skill-registryShowing 40 of 5,417 collected skills.
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions "RAG with DSPy", "context retrieval", "multi-hop RAG", or needs to build a DSPy…
This skill should be used when the user asks to "create a DSPy signature", "define inputs and outputs", "design a signature", "use InputField or OutputField", "add type hints to DSPy", mentions "signature class", "type-safe DSPy", "Pydantic models in DSPy",…
This skill should be used when the user asks to "optimize with SIMBA", "use Bayesian optimization", "optimize agents with custom feedback", mentions "SIMBA optimizer", "mini-batch optimization", "statistical optimization", "lightweight optimizer", or needs an…
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
This skill should be used when the user asks about "Effect AI", "@effect/ai", "LLM integration", "AI tool use", "AI execution planning", "building AI agents", "AI providers", "structured AI output", "AI completions", "Effect OpenAI", "Effect Anthropic", or…
@effect/ai integration patterns for categorical AI composition, typed error handling, and production prompt pipelines. Use when building AI applications with Effect-TS, composing LLM calls with typed errors, creating tool-augmented AI systems, or integrating…
Master effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, optimizing Claude interactions, or troubleshooting why Claude misunderstood a request. Covers @ mentions, thinking keywords, task framing,…
ElevenLabs Agents Platform for AI voice agents (React/JS/Native/Swift). Use for voice AI, RAG, tools, or encountering package deprecation, audio cutoff, CSP violations, webhook auth failures.
Generate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery.…
Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness
Profile AI engine superpowers and capability boundaries.
Transform simple prompts into comprehensive, context-aware prompts. Use for prompt enhancement, requirements analysis, and implementation strategy. Includes Context7 prompt engineering guides lookup.
Complete Eureka V6.1 Context Engineering suite with observability, structured output, and hybrid memory
Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.
Find AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark failures', 'close Python-AILANG gap', or after running evals.
Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.
Use Exa AI for neural search, content retrieval, and automated deep research. Requires EXA_API_KEY.
Execute the forged prompt exactly as written, with no reinterpretation. Requires explicit user consent and a ready prompt artifact on disk. Deletes the canonical prompt after successful execution.
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and learning from mistakes. Achieves continual learning for $18…
Extended thinking (ultrathink) configuration for Claude API. Activate for complex reasoning tasks, deep analysis, multi-step problem solving, and tasks requiring careful deliberation. Enables Claude's internal reasoning with configurable thinking budgets.
""
""
""
""
""
""
LLM APIs: OpenAI, Claude, Gemini, local LLMs, prompt engineering, function calling.
""
Build Model Context Protocol (MCP) servers - comprehensive coverage of generic MCP protocol AND FastMCP framework specialization. Use when creating any MCP server (Python FastMCP preferred, TypeScript/Node also covered). Includes agent-centric design…
FastMCP server patterns for building MCP servers. Use when implementing MCP tools, resources, or server configuration.
FastMCP Python framework for MCP servers with tools, resources, storage backends (memory/disk/Redis/DynamoDB). Use for Claude tool exposure, OAuth Proxy, cloud deployment, or encountering storage, lifespan, middleware, circular import, async errors.
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
Few-Shot Learning（少数例示学習）のパターンとベストプラクティスを提供するスキル。効果的な例示の設計、構造化、配置により、AIの出力品質を大幅に向上させます。 • The Pragmatic Programmer / 適用: 例示パターン設計の品質基準 / 目的: 実践的改善と一貫性維持 • Few-Shot戦略 / 適用: 段階的複雑度設計と最適shot数決定 / 目的: AIの学習効率最大化 Trigger: Use when you need to design effective…
Source text: Japanese
LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.
Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.
Shape, refine, and stabilize human intent into a canonical prompt artifact without executing anything. Iteratively clarifies ambiguity and contradictions until the user explicitly confirms readiness.
Apple Foundation Models framework for on-device AI, @Generable macro, guided generation, tool calling, and streaming. Use when user asks about on-device AI, Apple Intelligence, Foundation Models, @Generable, LLM, or local machine learning.
Detect friction signals; graduate patterns into rules. Use for session retrospectives.
Force full interview depth for this session. Use when user says '/full-interview' or 'full interview mode'.
LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.